This project addresses the complexity and time-intensiveness of auditing and optimizing paid advertising campaigns across multiple platforms. It provides a comprehensive skill for Claude Code, automating 190 checks and offering strategic planning templates, benefiting marketers and agencies by improving ad performance and efficiency.

How It Works

The system employs an orchestrator that routes commands to specialized sub-skills, enabling deep, single-domain analysis. For full audits, six parallel subagents concurrently analyze different aspects like Google Ads, Meta Ads, creative quality, tracking, budget, and compliance. It utilizes a Retrieval-Augmented Generation (RAG) pattern for on-demand loading of 12 reference files containing benchmarks and best practices, ensuring efficient and relevant analysis. Industry-specific templates further enhance strategic planning.

Quick Start & Requirements

• Installation:
  • Unix/macOS/Linux: curl -fsSL https://raw.githubusercontent.com/AgriciDaniel/claude-ads/main/install.sh | bash
  • Windows PowerShell: irm https://raw.githubusercontent.com/AgriciDaniel/claude-ads/main/install.ps1 | iex
  • Manual: git clone, cd claude-ads, then run ./install.sh (Unix) or .\install.ps1 (Windows).
• Prerequisites: Claude Code CLI, Python 3.10+. Playwright is optional for live landing page analysis.
• Demo Commands: /ads audit (full multi-platform audit), /ads google (Google Ads deep analysis), /ads plan saas (strategic planning for SaaS).

Highlighted Details

• 190 Audit Checks: Comprehensive coverage across Google, Meta, LinkedIn, TikTok, and Microsoft Ads, with weighted severity scoring.
• Ads Health Score: A unified score (0-100) generated from weighted checks, providing a prioritized action plan.
• Industry-Specific Templates: 11 templates for business types like SaaS, e-commerce, local-service, B2B, and more, offering tailored strategy frameworks.
• Quality Gates: Enforces hard rules during audits, including budget sufficiency, learning phase protection, CPA limits, and compliance checks for Special Ad Categories.
• Reference Data: Includes 12 built-in files with 2026-current benchmarks, bidding decision trees, and platform specifications.

Maintenance & Community

No specific details regarding notable contributors, sponsorships, or community channels (e.g., Discord, Slack) are provided in the README.

Licensing & Compatibility

The project is released under the MIT License, which generally permits commercial use and modification.

Limitations & Caveats

The provided README does not explicitly detail any limitations, alpha/beta status, known bugs, or unsupported platforms.